Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches

This study aims to evaluate the effectiveness of machine learning algorithms in predicting key forest metrics—stem volume, root system volume, and organ biomass (including leaves, branches, stem, and root)—for Pinus pseudostrobus var. Lindley, based on morphological measurements from the same trees....

Full description

Saved in:
Bibliographic Details
Main Authors: Pablo Antúnez, Christian Wehenkel, Erickson Basave-Villalobos, Celi Gloria Calixto-Valencia, César Valenzuela-Encinas, Faustino Ruiz-Aquino, David Sarmiento-Bustos
Format: Article
Language:English
Published: Taylor & Francis Group 2025-01-01
Series:Forest Science and Technology
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21580103.2025.2456295
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832577857699708928
author Pablo Antúnez
Christian Wehenkel
Erickson Basave-Villalobos
Celi Gloria Calixto-Valencia
César Valenzuela-Encinas
Faustino Ruiz-Aquino
David Sarmiento-Bustos
author_facet Pablo Antúnez
Christian Wehenkel
Erickson Basave-Villalobos
Celi Gloria Calixto-Valencia
César Valenzuela-Encinas
Faustino Ruiz-Aquino
David Sarmiento-Bustos
author_sort Pablo Antúnez
collection DOAJ
description This study aims to evaluate the effectiveness of machine learning algorithms in predicting key forest metrics—stem volume, root system volume, and organ biomass (including leaves, branches, stem, and root)—for Pinus pseudostrobus var. Lindley, based on morphological measurements from the same trees. The novelty of this study lies in applying five machine learning algorithms—Random Forest, Neural Networks, Gradient Boosting Machines, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN)—to predict these metrics, using data from the destructive analysis of 98 individual trees aged from eight months to five years. For comparison, we also applied univariate allometric models, adjusted with nonlinear least squares and quantile regression. The results indicate that Random Forest, k-NN, and SVM outperformed the other algorithms, demonstrating superior predictive accuracy for both biomass and volume. A key innovation of this study is its demonstration of how machine learning, with its ability to model complex, nonlinear relationships, can serve as a powerful tool for forest management. Quantile regression, combined with nonlinear least squares, proves most effective when the relationships are well-defined, allowing for tailored parameter adjustments that enhance predictions, particularly in the presence of heteroscedasticity.
format Article
id doaj-art-704db43af7644df49b6c8b5d76a3b779
institution Kabale University
issn 2158-0103
2158-0715
language English
publishDate 2025-01-01
publisher Taylor & Francis Group
record_format Article
series Forest Science and Technology
spelling doaj-art-704db43af7644df49b6c8b5d76a3b7792025-01-30T14:46:13ZengTaylor & Francis GroupForest Science and Technology2158-01032158-07152025-01-0111310.1080/21580103.2025.2456295Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric ApproachesPablo Antúnez0Christian Wehenkel1Erickson Basave-Villalobos2Celi Gloria Calixto-Valencia3César Valenzuela-Encinas4Faustino Ruiz-Aquino5David Sarmiento-Bustos6División de Estudios de Posgrado-Instituto de Estudios Ambientales, Universidad de la Sierra Juárez. Av. Universidad S/N, Oaxaca, México.;Instituto de Silvicultura e Industria de la Madera, Universidad Juárez del Estado de Durango, Durango, MéxicoINIFAP, CIR Norte-Centro, Campo Experimental Valle del Guadiana, Durango, MéxicoINIFAP, CIR Pacífico-Sur, Campo Experimental Iguala, Iguala de la Independencia, Guerrero, México.;División de Estudios de Posgrado-Instituto de Estudios Ambientales, Universidad de la Sierra Juárez. Av. Universidad S/N, Oaxaca, México.;División de Estudios de Posgrado-Instituto de Estudios Ambientales, Universidad de la Sierra Juárez. Av. Universidad S/N, Oaxaca, México.;Instituto de Estudios Ambientales, Universidad de la Sierra Juárez. Av. Universidad S/N, Oaxaca, MéxicoThis study aims to evaluate the effectiveness of machine learning algorithms in predicting key forest metrics—stem volume, root system volume, and organ biomass (including leaves, branches, stem, and root)—for Pinus pseudostrobus var. Lindley, based on morphological measurements from the same trees. The novelty of this study lies in applying five machine learning algorithms—Random Forest, Neural Networks, Gradient Boosting Machines, Support Vector Machines (SVM), and k-Nearest Neighbors (k-NN)—to predict these metrics, using data from the destructive analysis of 98 individual trees aged from eight months to five years. For comparison, we also applied univariate allometric models, adjusted with nonlinear least squares and quantile regression. The results indicate that Random Forest, k-NN, and SVM outperformed the other algorithms, demonstrating superior predictive accuracy for both biomass and volume. A key innovation of this study is its demonstration of how machine learning, with its ability to model complex, nonlinear relationships, can serve as a powerful tool for forest management. Quantile regression, combined with nonlinear least squares, proves most effective when the relationships are well-defined, allowing for tailored parameter adjustments that enhance predictions, particularly in the presence of heteroscedasticity.https://www.tandfonline.com/doi/10.1080/21580103.2025.2456295Forest managementmachine learning algorithms in forestrypredicting forest biomassRandom Forest algorithmallometric modelingquantile regression in forest management
spellingShingle Pablo Antúnez
Christian Wehenkel
Erickson Basave-Villalobos
Celi Gloria Calixto-Valencia
César Valenzuela-Encinas
Faustino Ruiz-Aquino
David Sarmiento-Bustos
Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches
Forest Science and Technology
Forest management
machine learning algorithms in forestry
predicting forest biomass
Random Forest algorithm
allometric modeling
quantile regression in forest management
title Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches
title_full Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches
title_fullStr Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches
title_full_unstemmed Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches
title_short Predictive Modeling of Volume and Biomass in Pinus pseudostrobus Using Machine Learning and Allometric Approaches
title_sort predictive modeling of volume and biomass in pinus pseudostrobus using machine learning and allometric approaches
topic Forest management
machine learning algorithms in forestry
predicting forest biomass
Random Forest algorithm
allometric modeling
quantile regression in forest management
url https://www.tandfonline.com/doi/10.1080/21580103.2025.2456295
work_keys_str_mv AT pabloantunez predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches
AT christianwehenkel predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches
AT ericksonbasavevillalobos predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches
AT celigloriacalixtovalencia predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches
AT cesarvalenzuelaencinas predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches
AT faustinoruizaquino predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches
AT davidsarmientobustos predictivemodelingofvolumeandbiomassinpinuspseudostrobususingmachinelearningandallometricapproaches